INDEX

Explanations

code-related syntax and structures

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Paglinawan

-0.66

 vincit

-0.57

 enfans

-0.55

 lørdag

-0.55

Exited

-0.54

 Tâm

-0.53

 affitto

-0.53

 barnen

-0.52

 octane

-0.52

 Autorizaciones

-0.51

POSITIVE LOGITS

0.67

TargetException

0.55

+");

0.53

 HttpNotFound

0.52

клопе

0.48

0.46

Po

0.46

TemporalType

0.45

Activations Density 0.024%

code-related syntax and structures

No Comments

No Known Activations